Google Colab链接https://colab.research.google.com/drive/115Qw0l5dhjlTtrbywMWRwhz9IxKE4_Dg?usp=sharing已过期。
信息：主:分布式环境：否
进程数：1
进程索引：0
本地进程索引：0
设备：cuda
混合精度类型：fp16
在配置中未找到'dynamic_thresholding_ratio','thresholding','prediction_type','variance_type','clip_sample_range','sample_max_value','timestep_spacing'。值将初始化为默认值。
[√] 随机种子设置为522721。
[√] 已加载提示：一个“hello world”的棋盘。
[√] encoder_hidden_states:torch.Size([4, 77, 768]).
[√] encoder_hidden_states_nocond:torch.Size([4, 77, 768]).
[√] 文本分词器成功加载。
[!] 从提示“a board of 'hello world'”检测到关键词['hello', 'world']
关键字索引x_min y_min x_max y_max
0 hello 98 127 296 235
1 world 67 240 416 348
[√] 成功生成布局
[√] character-level segmentation_mask:torch.Size([4, 256, 256]).
[√] feature_mask:torch.Size([4, 1, 64, 64]).
[√] masked_feature:torch.Size([4, 4, 64, 64]).
1
0%
0/50 [00:00<?, ?it/s]
tensor(981)
TypeErrorTraceback (most recent call last)
in <cell line: 4>()
2 classifier_free_scale = 7.5
3 sample_steps = 50
----> 4 main(prompt=prompt, classifier_free_scale=classifier_free_scale, sample_steps=sample_steps)
1 frames
/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py in _call_impl(self, *args, **kwargs)
1499 or _global_backward_pre_hooks or _global_backward_hooks
1500 or _global_forward_hooks or _global_forward_pre_hooks):
-> 1501 return forward_call(*args, **kwargs)
1502 # Do not call functions when jit is used
1503 full_backward_hooks, non_full_backward_hooks = [], []
TypeError: UNet2DConditionModel.forward()收到了一个意外的关键字参数'segmentation_mask'